Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1659 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.3768. Min Range: -3.3768

Max Act: 3.3768. Min Act: -0.0000

Data Index: 416180 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.6054. Min Act: -0.0000

Data Index: 1149619 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.5952. Min Act: -0.0000

Data Index: 1518924 (Python Code)

Max Activating Token Index: 184

Text #3

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.3948. Min Act: -0.0000

Data Index: 262507 (C4 (Web Text))

Max Activating Token Index: 174

Text #4

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.3651. Min Act: -0.0000

Data Index: 1451677 (Python Code)

Max Activating Token Index: 805

Text #5

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.1108. Min Act: -0.0000

Data Index: 1387972 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.2913. Min Act: -0.0000

Data Index: 1531657 (Python Code)

Max Activating Token Index: 751

Text #7

Max Range: 3.3768. Min Range: -3.3768

Max Act: 2.0387. Min Act: -0.0000

Data Index: 1492241 (Python Code)

Max Activating Token Index: 387

Text #8

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.9759. Min Act: -0.0000

Data Index: 359385 (C4 (Web Text))

Max Activating Token Index: 914

Text #9

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.9802. Min Act: -0.0000

Data Index: 1584028 (Python Code)

Max Activating Token Index: 16

Text #10

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.8762. Min Act: -0.0000

Data Index: 53762 (C4 (Web Text))

Max Activating Token Index: 358

Text #11

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.8841. Min Act: -0.0000

Data Index: 1442793 (Python Code)

Max Activating Token Index: 701

Text #12

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.8520. Min Act: -0.0000

Data Index: 1468935 (Python Code)

Max Activating Token Index: 533

Text #13

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.9555. Min Act: -0.0000

Data Index: 1405527 (Python Code)

Max Activating Token Index: 585

Text #14

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.9340. Min Act: -0.0000

Data Index: 1419935 (Python Code)

Max Activating Token Index: 865

Text #15

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.9473. Min Act: -0.0000

Data Index: 1433100 (Python Code)

Max Activating Token Index: 576

Text #16

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.8066. Min Act: -0.0000

Data Index: 1522199 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.9147. Min Act: -0.0000

Data Index: 1651507 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.9031. Min Act: -0.0000

Data Index: 1648296 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 3.3768. Min Range: -3.3768

Max Act: 1.7843. Min Act: -0.0000

Data Index: 1553697 (Python Code)

Max Activating Token Index: 891